Research organizations with GPT‑5, Gemini, CourtListener, LegiScan and OSINT web sources
Needs changesWhat this workflow does
This AI workflow has 53 nodes and runs when another workflow calls it (plus 1 other trigger). Along the way it connects HTTP Request, Jina AI, OpenRouter Chat Model and Weaviate Vector Store and 1 more. It also calls google.serper.dev and api.scrapingdog.com over HTTP.
How it runs
Trigger: When another workflow calls it (plus 1 other trigger).
- Set Prompt (Edit Fields (Set)): sets 4 fields: companyName, companyDomain, reportGoal…
- Looking for Sources (AI Agent): runs an AI agent, with model: Auto Fallback, Gemini 2.5 Flash; 6 tools (Open Corporates, LegiScan Discovery, DocumentCloud Dsicovery, Google Search Discovery…)
- Retry if Tools Not Used (If): checks a condition and branches into true / false
- Prioritizing Sources (AI Agent): runs an AI agent, with model: GPT-5a, Auto Fallback; 1 tool (Think Tool)
- Retry if Response Empty (If): checks a condition and branches into true / false
- Investigating Sources Further (AI Agent): runs an AI agent, with model: Auto Fallback, Gemini 2.5 Flash; 9 tools (BuiltWith, Open Corporates, LegiScan Retrieval, DocumentCloud Retrieval…)
- Retry if Tools Not Used (If): checks a condition and branches into true / false
- Writing Report (AI Agent): runs an AI agent, with model: GPT-5b, Auto Fallback; 1 tool (Think Tool)
- Retry if Response Empty (If): checks a condition and branches into true / false
- Set Report (Edit Fields (Set)): sets 2 fields: Final Report, Retrieved Documents
…plus 9 more steps. See the full node list below.
Services it uses
HTTP calls to: google.serper.dev, api.scrapingdog.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- HTTP Request Tool (legacy) in Google Search Discovery, Twitter Profile Scraper1, Linkedin Person and Company Scraper1…: replace with HTTP Request node connected to the AI Agent's Tool input.
| Removed in 3.0 | Replace with |
|---|---|
| HTTP Request Tool (legacy) Google Search Discovery, Twitter Profile Scraper1, Linkedin Person and Company Scraper1, Instagram Profile Scraper1 | HTTP Request node connected to the AI Agent's Tool input |
Nodes used (15)
- Http Request Tool
n8n-nodes-base.httpRequestTool - HTTP Request Tool
@n8n/n8n-nodes-langchain.toolHttpRequest - Think Tool
@n8n/n8n-nodes-langchain.toolThink - Jina Ai Tool
n8n-nodes-base.jinaAiTool - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - If
n8n-nodes-base.if - Edit Fields (Set)
n8n-nodes-base.set - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - AI Agent
@n8n/n8n-nodes-langchain.agent - Weaviate Vector Store
@n8n/n8n-nodes-langchain.vectorStoreWeaviate - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Respond to Webhook
n8n-nodes-base.respondToWebhook - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Webhook
n8n-nodes-base.webhook
From the author
Who is this for This workflow is designed for researchers, investigators, and analysts who need to: - Build comprehensive profiles of organizations from public sources - Research court cases, legislation, and government documents related to companies - Verify…